Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    demonstrative adjectives / technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    恝
    0.50
     бясплат
    0.48
    伀
    0.48
     गुलाब
    0.48
    杝
    0.46
    łożyć
    0.45
    сё
    0.45
    кмекер
    0.45
    ᆹ
    0.44
    zględ
    0.44
    POSITIVE LOGITS
     aceste
    0.60
     this
    0.56
     ذلك
    0.50
     technology
    0.50
     cette
    0.49
     هذا
    0.49
     प्रौद्योगिकी
    0.49
     dieses
    0.48
     هذه
    0.48
    これは
    0.48
    Act Density 0.001%

    No Known Activations